Deep Convolutional Neural Network Model Research Articles

Ultrasonographic diagnosis of ovarian tumors through the deep convolutional neural network.

The objective of this study was to develop and validate an ovarian tumor ultrasonographic diagnostic model based on deep convolutional neural networks (DCNN) and compare its diagnostic performance with that of human experts. We collected 486 ultrasound images of 192 women with malignant ovarian tumors and 617 ultrasound images of 213 women with benign ovarian tumors, all confirmed by pathological examination. The image dataset was split into a training set and a validation set according to a 7:3 ratio. We selected 5 DCNNs to develop our model: MobileNet, Xception, Inception, ResNet and DenseNet. We compared the performance of the five models through the area under the curve (AUC), sensitivity, specificity, and accuracy. We then randomly selected 200 images from the validation set as the test set. We asked three expert radiologists to diagnose the images to compare the performance of radiologists and the DCNN model. In the validation set, AUC of DenseNet was 0.997 while AUC was 0.988 of ResNet, 0.987 of Inception, 0.968 of Xception and 0.836 of MobileNet. In the test set, the accuracy was 0.975 with the DenseNet model versus 0.825 (p < 0.0001) with the radiologists, and sensitivity was 0.975 versus 0.700 (p < 0.0001), and specificity was 0.975 versus 0.908 (p < 0.001). DensNet performed better than other DCNNs and expert radiologists in identifying malignant ovarian tumors from benign ovarian tumors based on ultrasound images, a finding that needs to be further explored in clinical trials.

Diagnosis of Osteoporosis Using Transfer Learning in the Same Domain

This paper presents a system for diagnosing osteoporosis using x-rays by leveraging transfer learning in the same domain. The proposed system consists of phase 1 and phase 2; each phase includes several stages, as the pre-processing stage appropriately prepares the source image via noise reduction by the average filter, contrast enhancement using histogram equalization, and obtaining the region of interest by employing K-mean and edge detection, followed by the smudging stage through a mean filter with a large window size, which subsequently contributed to facilitating the diagnosis. The stages mentioned in both phases are similar. In phase 1, the model is trained on a large unlabeled x-ray dataset collected from different orthopedic centers to identify the general features of the image. In phase 2, fine-tune the trained model with the target dataset; this approach is beneficial when the target task has limited labeled data or when training a model from scratch is computationally expensive. It is worth noting that two datasets were used as target datasets. The accuracy of diagnosing osteoporosis using the proposed deep convolutional neural network (DCNN) model was 94.5 with the osteoporosis knee x-ray database (Dataset A). The accuracy of diagnosing osteoporosis using transfer learning in the same field was 98.91 when training the proposed DCNN model with a large unlabeled dataset and fine-tuning with the target database, osteoporosis knee x-ray database (Dataset A). The accuracy of diagnosing osteoporosis using the proposed DCNN model was 91.5 with the knee x-ray osteoporosis database (Dataset B). The accuracy of diagnosing osteoporosis using transfer learning in the same field was 96.61 when training the proposed DCNN model with a large unlabeled dataset and fine-tuning with the target knee x-ray osteoporosis database (Dataset B).

Optimized Dropkey-Based Grad-CAM: Toward Accurate Image Feature Localization.

Regarding the interpretable techniques in the field of image recognition, Grad-CAM is widely used for feature localization in images to reflect the logical decision-making information behind the neural network due to its high applicability. However, extensive experimentation on a customized dataset revealed that the deep convolutional neural network (CNN) model based on Gradient-weighted Class Activation Mapping (Grad-CAM) technology cannot effectively resist the interference of large-scale noise. In this article, an optimization of the deep CNN model was proposed by incorporating the Dropkey and Dropout (as a comparison) algorithm. Compared with Grad-CAM, the improved Grad-CAM based on Dropkey applies an attention mechanism to the feature map before calculating the gradient, which can introduce randomness and eliminate some areas by applying a mask to the attention score. Experimental results show that the optimized Grad-CAM deep CNN model based on the Dropkey algorithm can effectively resist large-scale noise interference and achieve accurate localization of image features. For instance, under the interference of a noise variance of 0.6, the Dropkey-enhanced ResNet50 model achieves a confidence level of 0.878 in predicting results, while the other two models exhibit confidence levels of 0.766 and 0.481, respectively. Moreover, it exhibits excellent performance in visualizing tasks related to image features such as distortion, low contrast, and small object characteristics. Furthermore, it has promising prospects in practical computer vision applications. For instance, in the field of autonomous driving, it can assist in verifying whether deep learning models accurately understand and process crucial objects, road signs, pedestrians, or other elements in the environment.

Deep convolutional neural network with fusion strategy for skin cancer recognition: model development and validation

We aimed to develop an accurate and efficient skin cancer classification system using deep-learning technology with a relatively small dataset of clinical images. We proposed a novel skin cancer classification method, SkinFLNet, which utilizes model fusion and lifelong learning technologies. The SkinFLNet's deep convolutional neural networks were trained using a dataset of 1215 clinical images of skin tumors diagnosed at Taichung and Taipei Veterans General Hospital between 2015 and 2020. The dataset comprised five categories: benign nevus, seborrheic keratosis, basal cell carcinoma, squamous cell carcinoma, and malignant melanoma. The SkinFLNet's performance was evaluated using 463 clinical images between January and December 2021. SkinFLNet achieved an overall classification accuracy of 85%, precision of 85%, recall of 82%, F-score of 82%, sensitivity of 82%, and specificity of 93%, outperforming other deep convolutional neural network models. We also compared SkinFLNet's performance with that of three board-certified dermatologists, and the average overall performance of SkinFLNet was comparable to, or even better than, the dermatologists. Our study presents an efficient skin cancer classification system utilizing model fusion and lifelong learning technologies that can be trained on a relatively small dataset. This system can potentially improve skin cancer screening accuracy in clinical practice.

Optimal design of one-dimensional elastic metamaterials through deep convolutional neural network and genetic algorithm

Deep learning (DL) has found extensive application in elastic metamaterial design. However, these methods are often limited to fixed design parameters and single structural configuration, lacking versatility. To overcome these, we propose a novel data-driven design framework combining deep convolutional neural network (DCNN) and genetic algorithm (GA) to design vibration-isolating metamaterial structures in foundations. This framework is highly adaptable, accommodating diverse design parameters by identical models. We discretize different structural configurations into a uniform tensor format, and generate multiple datasets. Two DCNN-based forward prediction models are then developed to accurately capture bandgap distributions for all body waves. Additionally, we incorporate multiple populations to enhance the parallel search capacity of GA, and integrate it with the trained DCNN models to simultaneously determine multiple optimal structures. The optimal design result for different parameters shows that the designed structures can achieve the target bandgap, and proves the effectiveness and generality of our method. Finally, through the design of two structural configurations, we find that four-layer structure exhibits wider low-frequency bandgaps and superior vibration reduction performance compared to the three-layer structure, under the same material composition and usage.

Morphological diagnosis of hematologic malignancy using feature fusion-based deep convolutional neural network

Leukemia is a cancer of white blood cells characterized by immature lymphocytes. Due to blood cancer, many people die every year. Hence, the early detection of these blast cells is necessary for avoiding blood cancer. A novel deep convolutional neural network (CNN) 3SNet that has depth-wise convolution blocks to reduce the computation costs has been developed to aid the diagnosis of leukemia cells. The proposed method includes three inputs to the deep CNN model. These inputs are grayscale and their corresponding histogram of gradient (HOG) and local binary pattern (LBP) images. The HOG image finds the local shape, and the LBP image describes the leukaemia cell's texture pattern. The suggested model was trained and tested with images from the AML-Cytomorphology_LMU dataset. The mean average precision (MAP) for the cell with less than 100 images in the dataset was 84%, whereas for cells with more than 100 images in the dataset was 93.83%. In addition, the ROC curve area for these cells is more than 98%. This confirmed proposed model could be an adjunct tool to provide a second opinion to a doctor.

Co-embedding of edges and nodes with deep graph convolutional neural networks

Graph neural networks (GNNs) have significant advantages in dealing with non-Euclidean data and have been widely used in various fields. However, most of the existing GNN models face two main challenges: (1) Most GNN models built upon the message-passing framework exhibit a shallow structure, which hampers their ability to efficiently transmit information between distant nodes. To address this, we aim to propose a novel message-passing framework, enabling the construction of GNN models with deep architectures akin to convolutional neural networks (CNNs), potentially comprising dozens or even hundreds of layers. (2) Existing models often approach the learning of edge and node features as separate tasks. To overcome this limitation, we aspire to develop a deep graph convolutional neural network learning framework capable of simultaneously acquiring edge embeddings and node embeddings. By utilizing the learned multi-dimensional edge feature matrix, we construct multi-channel filters to more effectively capture accurate node features. To address these challenges, we propose the Co-embedding of Edges and Nodes with Deep Graph Convolutional Neural Networks (CEN-DGCNN). In our approach, we propose a novel message-passing framework that can fully integrate and utilize both node features and multi-dimensional edge features. Based on this framework, we develop a deep graph convolutional neural network model that prevents over-smoothing and obtains node non-local structural features and refined high-order node features by extracting long-distance dependencies between nodes and utilizing multi-dimensional edge features. Moreover, we propose a novel graph convolutional layer that can learn node embeddings and multi-dimensional edge embeddings simultaneously. The layer updates multi-dimensional edge embeddings across layers based on node features and an attention mechanism, which enables efficient utilization and fusion of both node and edge features. Additionally, we propose a multi-dimensional edge feature encoding method based on directed edges, and use the resulting multi-dimensional edge feature matrix to construct a multi-channel filter to filter the node information. Lastly, extensive experiments show that CEN-DGCNN outperforms a large number of graph neural network baseline methods, demonstrating the effectiveness of our proposed method.

An effective correlation-based data modeling framework for automatic diabetes prediction using machine and deep learning techniques

The rising risk of diabetes, particularly in emerging countries, highlights the importance of early detection. Manual prediction can be a challenging task, leading to the need for automatic approaches. The major challenge with biomedical datasets is data scarcity. Biomedical data is often difficult to obtain in large quantities, which can limit the ability to train deep learning models effectively. Biomedical data can be noisy and inconsistent, which can make it difficult to train accurate models. To overcome the above-mentioned challenges, this work presents a new framework for data modeling that is based on correlation measures between features and can be used to process data effectively for predicting diabetes. The standard, publicly available Pima Indians Medical Diabetes (PIMA) dataset is utilized to verify the effectiveness of the proposed techniques. Experiments using the PIMA dataset showed that the proposed data modeling method improved the accuracy of machine learning models by an average of 9%, with deep convolutional neural network models achieving an accuracy of 96.13%. Overall, this study demonstrates the effectiveness of the proposed strategy in the early and reliable prediction of diabetes.

Face Mask Image Classification Using Fine-Tuning and The Effect of FGSM And PGD Attacks.

This research seeks to use a fine-tuning method for automatic diagnostics and classification of face masks without face mask images. We trained Deep Convolutional Neural Network models on the face mask dataset obtained from the Mendeley data repository to determine whether individuals will adhere to policies that face mask reduces the spread of SARS-COV-2. The proposed architectures used in this study include the VGG19, MobileNetV3, and InceptionV3 models. These models are known for their role in classifying images. They were trained using the fine-tuning approach and their respective outputs were compared. After training the face mask dataset, it can be said that the fine-tuned InceptionV3 model performed extremely well against the other models obtaining an accuracy of 99.21%, and was able to predict 99.63% of the test dataset. However, the robustness of the fine-tuned model was tested against fast gradient sign method (FGSM) and projected gradient descent (PGD) attacks which generate adversarial images using the gradients of the model. Additionally, the classification report shows after the FGSM attack that the model's accuracy was reduced by 43%. Also, after the PDG attack, the accuracy of the model was reduced by 19%. We assessed the models using many performance metrics such as precision, recall, F1 score, and accuracy before subjecting them to two common adversarial attack techniques: FGSM and PDG. Finally, we demonstrated how the proposed robust method improved the model’s defense against adversarial attacks. The findings emphasize the critical need to increase awareness about adversarial assaults on SARS-COV-2 monitoring systems and to advocate for proactive steps to protect healthcare systems from comparable threats prior to practical deployment.

Speech emotion recognition and classification using hybrid deep CNN and BiLSTM model

Speech emotion recognition and classification using hybrid deep CNN and BiLSTM model

Stacking ensemble learning for optical music recognition

The development of music culture has resulted in a problem called optical music recognition (OMR). OMR is a task in computer vision that explores the algorithms and models to recognize musical notation. This study proposed the stacking ensemble learning model to complete the OMR task using the common western musical notation (CWMN) musical notation. The ensemble learning model used four deep convolutional neural networks (DCNNs) models, namely ResNeXt50, Inception-V3, RegNetY-400MF, and EfficientNet-V2-S as the base classifier. This study also analysed the most appropriate technique to be used as the ensemble learning model’s meta-classifier. Therefore, several machine learning techniques are determined to be evaluated, namely support vector machine (SVM), logistic regression (LR), random forest (RF), K-nearest neighbor (KNN), decision tree (DT), and Naïve Bayes (NB). Six publicly available OMR datasets are combined, down sampled, and used to test the proposed model. The dataset consists of the HOMUS_V2, Rebelo1, Rebelo2, Fornes, OpenOMR, and PrintedMusicSymbols datasets. The proposed ensemble learning model managed to outperform the model built in the previous study and succeeded in achieving outstanding accuracy and F1-scores with the best value of 97.51% and 97.52%, respectively; both of which were achieved by the LR meta-classifier.

Towards Transmission-Friendly and Robust CNN Models over Cloud and Device

Deploying deep convolutional neural network (CNN) models on ubiquitous Internet of Things (IoT) devices has attracted much attention from industry and academia since it greatly facilitates our lives by providing various rapid-response services. Due to the limited resources of IoT devices, cloud-assisted training of CNN models has become the mainstream. However, most existing related works suffer from a large amount of model parameter transmission and weak model robustness. To this end, this paper proposes a cloud-assisted CNN training framework with low model parameter transmission and strong model robustness. In the proposed framework, we first introduce MonoCNN, which contains only a few learnable filters, and other filters are nonlearnable. These nonlearnable filter parameters are generated according to certain rules, i.e., the filter generation function (FGF), and can be saved and reproduced by a few random seeds. Thus, the cloud server only needs to send these learnable filters and a few seeds to the IoT device. Compared to transmitting all model parameters, sending several learnable filter parameters and seeds can significantly reduce parameter transmission. Then, we investigate multiple FGFs and enable the IoT device to use the FGF to generate multiple filters and combine them into MonoCNN. Thus, MonoCNN is affected not only by the training data but also by the FGF. The rules of the FGF play a role in regularizing the MonoCNN, thereby improving its robustness. Experimental results show that compared to state-of-the-art methods, our proposed framework can reduce a large amount of model parameter transfer between the cloud server and the IoT device while improving the performance by approximately 2.2% when dealing with corrupted data. The code is available at https://github.com/evoxlos/mono-cnn-pytorch.

Efficient pollen grain classification using pre-trained Convolutional Neural Networks: a comprehensive study

Pollen identification is necessary for several subfields of geology, ecology, and evolutionary biology. However, the existing methods for pollen identification are laborious, time-consuming, and require highly skilled scientists. Therefore, there is a pressing need for an automated and accurate system for pollen identification, which can be beneficial for both basic research and applied issues such as identifying airborne allergens. In this study, we propose a deep learning (DL) approach to classify pollen grains in the Great Basin Desert, Nevada, USA. Our dataset consisted of 10,000 images of 40 pollen species. To mitigate the limitations imposed by the small volume of our training dataset, we conducted an in-depth comparative analysis of numerous pre-trained Convolutional Neural Network (CNN) architectures utilizing transfer learning methodologies. Simultaneously, we developed and incorporated an innovative CNN model, serving to augment our exploration and optimization of data modeling strategies. We applied different architectures of well-known pre-trained deep CNN models, including AlexNet, VGG-16, MobileNet-V2, ResNet (18, 34, and 50, 101), ResNeSt (50, 101), SE-ResNeXt, and Vision Transformer (ViT), to uncover the most promising modeling approach for the classification of pollen grains in the Great Basin. To evaluate the performance of the pre-trained deep CNN models, we measured accuracy, precision, F1-Score, and recall. Our results showed that the ResNeSt-110 model achieved the best performance, with an accuracy of 97.24%, precision of 97.89%, F1-Score of 96.86%, and recall of 97.13%. Our results also revealed that transfer learning models can deliver better and faster image classification results compared to traditional CNN models built from scratch. The proposed method can potentially benefit various fields that rely on efficient pollen identification. This study demonstrates that DL approaches can improve the accuracy and efficiency of pollen identification, and it provides a foundation for further research in the field.

Application of bone alkaline phosphatase and 25-oxhydryl-vitamin D in diagnosis and prediction of osteoporotic vertebral compression fractures

BackgroundOsteoporosis is a bone metabolic disease that usually causes fracture. The improvement of the clinical diagnostic efficiency of osteoporosis is of great significance for the prevention of fracture. The predictive and diagnostic values of bone alkaline phosphatase (B-ALP) and 25-oxhydryl-vitamin D (25-OH-VD) for osteoporotic vertebral compression fractures (OVCFs) were evaluated.Methods110 OVCFs patients undergoing percutaneous vertebroplasty were included as subjects and their spinal computed tomography (CT) images were collected. After that, deep convolutional neural network model was employed for intelligent fracture recognition. Next, the patients were randomly enrolled into Ctrl group (65 cases receiving postoperative routine treatment) and VD2 group (65 cases injected with vitamin D2 into muscle after the surgery). In addition, 100 healthy people who participated in physical examination were included in Normal group. The differences in Oswestry dysfunction indexes (ODI), imaging parameters, B-ALP and 25-OH-VD expressions, and quality of life (QOL) scores of patients among the three groups were compared. The values of B-ALP and 25-OH-VD in predicting and diagnosing OVCFs and their correlation with bone density were analyzed.ResultsIt was demonstrated that computer intelligent medical image technique was more efficient in fracture CT recognition than artificial recognition. In contrast to those among patients in Normal group, B-ALP rose while 25-OH-VD declined among patients in Ctrl and VD2 groups (P < 0.05). Versus those among patients in Ctrl group, ODI, Cobb angle, and B-ALP reduced, while bone density, the height ratio of the injured vertebrae, 25-OH-VD, and QOL score increased among patients in VD2 group after the treatment (P < 0.05). The critical values, accuracy, and areas under the curve (AUC) of the diagnosis of OVCFs by B-ALP and 25-OH-VD amounted to 87.8 μg/L versus 30.3 nmol/L, 86.7% versus 83.3%, and 0.86 versus 0.82, respectively. B-ALP was apparently negatively correlated with bone density (r = − 0.602, P < 0.05), while 25-OH-VD was remarkably positively correlated with bone density (r = 0.576, P < 0.05).ConclusionTo sum up, deep learning-based computer CT image intelligent detection technique could improve the diagnostic efficacy of fracture. B-ALP rose while 25-OH-VD declined among patients with OVCFs and OVCFs could be predicted and diagnosed based on B-ALP and 25-OH-VD. Postoperative intramuscular injection of VD2 could effectively improve the therapeutic effect on patients with OVCFs and QOL.

Blind deep-learning based preprocessing method for Fourier ptychographic microscopy

Fourier ptychographic microscopy (FPM) is a technique for tackling the trade-off between the resolution and the imaging field of view by combining the techniques from aperture synthesis and phase retrieval to estimate the complex object from a series of low-resolution intensity images captured under angle-varied illumination. The captured images are commonly corrupted by multiple noise, leading to the degradation of the reconstructed image quality. Typically speaking, the noise model and noise level of the experimental images are unknown, and the traditional image denoising methods have limited effect. In this paper we model the FPM forward imaging process corrupted by noise and divide the noise in the captured images into two parts: the signal-dependent part and the signal-independent part. Based on the noise model we propose a novel blind deep-learning based Fourier ptychographic microscopy preprocessing method, termed BDFP, for removing these two components of noise. First, from a portion of the captured low-resolution images, a set of blocks corresponding to the smooth area of the object are extracted to model signal-independent noise. Second, under the assumption that the signal-dependent noise follows a Poisson distribution, we add Poisson noise and signal-independent noise blocks to clean images to form a paired training dataset, which is then used for training a deep convolutional neural network (CNN) model to reduce both signal-dependent noise and signal-independent noise. The proposed blind preprocessing method, combining with typical FPM reconstruction algorithms, is tested on simulated data and experimental images. Experimental results show that our preprocessing method can significantly reduce the noise in the captured images and bring about effective improvements in reconstructed image quality.

Deep Multi-Branch CNN Architecture for Early Alzheimer's Detection from Brain MRIs.

Alzheimer's disease (AD) is a neurodegenerative disease that can cause dementia and result in a severe reduction in brain function, inhibiting simple tasks, especially if no preventative care is taken. Over 1 in 9 Americans suffer from AD-induced dementia, and unpaid care for people with AD-related dementia is valued at USD 271.6 billion. Hence, various approaches have been developed for early AD diagnosis to prevent its further progression. In this paper, we first review other approaches that could be used for the early detection of AD. We then give an overview of our dataset and propose a deep convolutional neural network (CNN) architecture consisting of 7,866,819 parameters. This model comprises three different convolutional branches, each having a different length. Each branch is comprised of different kernel sizes. This model can predict whether a patient is non-demented, mild-demented, or moderately demented with a 99.05% three-class accuracy. In summary, the deep CNN model demonstrated exceptional accuracy in the early diagnosis of AD, offering a significant advancement in the field and the potential to improve patient care.

An Automatic Non-Destructive External and Internal Quality Evaluation of Mango Fruits based on Color and X-ray Imaging with Machine Learning and Deep Learning Based Classification Models

Quality evaluation of food products, agricultural produce to be specific, has gained momentum from past few decades due to the increased awareness among consumers across the world. This has resulted in the increased emphasis on the development and use of quality assessment techniques in food industry. Moreover, there is a need to automate the quality monitoring of agricultural produce like fruits and vegetables which is otherwise done manually in developing countries hence labor intensive, time consuming and subjective in nature. This paper presents an empirical analysis to build a rapid, robust, real-time, non-destructive computer vision based quality assessment model for mango fruits. The work employs the automatic disease classification of mango fruits based on machine and deep learning models. Firstly, the dataset of colored mango fruits images with 2279 images falling into three classes and another dataset of soft X-ray images of mango fruits with 572 images belonging to two quality classes are developed for detecting external and internal defects, respectively. The multilayer perceptron neural network (MLP NN) with two hidden layers, which may be considered as the starting point for deep learning technique, is proposed as machine learning model to classify the color images of mango fruits into one of three external quality classes with 95.1% accuracy and also to classify the soft X-ray images into two internal quality classes with 97.5% accuracy. In order to step out of feature engineering, actual deep learning convolutional neural network (CNN) models, a customized CNN model and pre-trained CNN models, VGGNet (VGG16) and DenseNet121 were also explored for mango disease classification. The maximum validation accuracy of custom CNN was found to be with 91.52% and 98.7% for color and augmented X-ray images, respectively. The classification accuracy of pre-trained models were found to be reasonably good for the color images but exhibited high variability in results and made it difficult to draw a general conclusion for the proposed datasets. However, the proposed MLP NN model based on few basic intensity and geometric features and also the proposed customized CNN model were found to be the best models and they outperform the state of the art reported in the literature.

A concatenation approach-based disease prediction model for sustainable health care system

In the present world, due to many factors like environmental changes, food styles, and living habits, human health is constantly affected by different diseases, which causes a huge amount of data to be managed in health care. Some diseases become life-threatening if they are not cured at the starting stage. Thus, it is a complex task for the healthcare system to design a well-trained disease prediction model for accurately identifying diseases. Deep learning models are the most widely used in disease prediction research, but their performance is inferior to conventional models. In order to overcome this issue, this work introduces the concatenation of Inception V3 and Xception deep learning convolutional neural network models. The proposed model extracts the main features and produces the prediction result more accurately than traditional predictive models. This work analyses the performance of the proposed model in terms of accuracy, precision, recall, and f1-score. It compares the proposed model to existing techniques such as Stacked Denoising Auto-Encoder (SDAE), Logistic Regression (LR), MLP, MLP with attention mechanism (MLP-A), Support Vector Machine (SVM), Multi Neural Network (MNN), and Hybrid Convolutional Neural Network (CNN)-Random Forest (RF).

Optimized Deep Learning Model for Disease Prediction in Potato Leaves

Food crops are important for nations and human survival. Potatoes are one of the most widely used foods globally. But there are several diseases hampering potato growth and production as well. Traditional methods for diagnosing disease in potato leaves are based on human observations and laboratory tests which is a cumbersome and time-consuming task. The new age technologies such as artificial intelligence and deep learning can play a vital role in disease detection. This research proposed an optimized deep learning model to predict potato leaf diseases. The model is trained on a collection of potato leaf image datasets. The model is based on a deep convolutional neural network architecture which includes data augmentation, transfer learning, and hyper-parameter tweaking used to optimize the proposed model. Results indicate that the optimized deep convolutional neural network model has produced 99.22% prediction accuracy on Potato Disease Leaf Dataset.

SeNet-I: An approach for detecting network intrusions through serialized network traffic images

The exponential growth of the internet and inter-connectivity has resulted in an extensive increase in network size and the corresponding data, which has led to numerous novel attacks that pose significant challenges to network security. However, conventional network security approaches predominantly rely on the metadata of network traffic, utilized in numeric form, which is becoming ineffective against new attacks that hide within the content of the traffic. Therefore, it raises the need for security systems to adapt to the changing dynamics of network attacks. To address this issue, we propose a new approach called SeNet-I that leverages computer vision capabilities to combine low-level features and develop a more abstract and high-level representation of network traffic without requiring feature engineering. The proposed approach utilizes the raw network traffic information and transforms it into serialized three-channel images, which are employed as input to a proposed deep concatenated convolutional neural network model. Additionally, SeNet-I can easily incorporate packet level information, which is often challenging for conventional approaches due to its high dimensionality. To demonstrate the effectiveness of the proposed approach, we tested SeNet-I on both packet-based and flow-based network traffic, comparing it with current state-of-the-art methods and different image-based approaches. With F1 scores of 96% and 83% achieved in the multi-class classification of flow-based and packet-based network intrusion detection, our proposed approach outperformed other existing methods in the literature. Lastly, we discussed the advantages and limitations of the proposed method.